BACKGROUND AND AIMS:Identification of patients with acute coronary syndrome requiring coronary revascularization can be challenging due to inconclusive electrocardiogram (ECG) findings or biomarker results. A deep learning model to detect ECG patterns associated with revascularization likelihood was developed, aiming to guide further assessment and reduce diagnostic uncertainty. METHODS:A convolutional neural network model was trained on 144 691 ED visits from a US cohort (60 ± 19 years; 53% female; 0.6% revascularization), tested on a separate test cohort (n = 35 995), and benchmarked against clinician ECG interpretation and cardiac troponin T (TnT). External validation was performed for the outcomes revascularization and Type 1 myocardial infarction (MI) on 18 673 ED visits from Europe (55 ± 21 years; 49% female; 1.5% revascularization; 1% Type 1 MI). Primary performance metric was area under the receiver operating characteristic curve (AUROC). RESULTS:In the test cohort, the model achieved an AUROC of 0.91 (95% confidence interval [CI] 0.91-0.91), outperforming clinician ECG interpretation (AUROC 0.65, 95% CI 0.54-0.76) and conventional cardiac TnT (AUROC 0.71). In the external validation cohort, ECG model AUROC was 0.81 (95% CI 0.81-0.82) for revascularization, and 0.85 (95% CI 0.84-0.85) for Type 1 MI, compared with 0.70 (95% CI 0.57-0.83) and 0.74 (95% CI 0.56-0.92) for clinician interpretation, and 0.85 and 0.87 for high-sensitivity (hs)-TnT, respectively. The ECG model had higher specificity but lower sensitivity compared with high-sensitivity-troponin T. CONCLUSIONS:The model was able to detect revascularization and Type 1 MI with competitive performance, suggesting a potential role to complement current clinical assessment.

Atrial tachycardias (AT) represent an increasingly common cause of morbidity and mortality. Driven by substantial advances in mapping and ablation technologies, the mechanistic understanding and therapeutic strategies for AT management have evolved rapidly in recent years, and catheter ablation is now regarded as the most effective strategy for maintaining sinus rhythm. Against this background, the recently published international clinical consensus statement on the management of patients with AT introduces, for the first time, a structured 10-point plan for "SMART-AT care" as a framework for the diagnosis and treatment of regular AT. This review highlights key developments and clinical implications, taking into account recent changes within the healthcare system.

Atriale Tachykardien (AT) sind eine zunehmend häufige Ursache für Morbidität und Mortalität. Aufgrund substanzieller Fortschritte in Mapping- und Ablationstechnologien haben sich das elektrophysiologische Verständnis und die therapeutischen Konzepte im Rahmen der Behandlung von AT in den vergangenen Jahren rasch weiterentwickelt, sodass die Katheterablation heute als effektivste Methode zum Rhythmuserhalt gilt. Vor diesem Hintergrund legt das kürzlich veröffentlichte, von internationalen Fachgesellschaften erarbeitete Konsensusdokument zum Management von Patienten mit AT erstmals einen strukturierten 10-Punkte-Plan für „SMART-AT care“ als Rahmen für Diagnostik und Therapie regulärer AT vor. In der vorliegenden Übersicht werden wesentliche Neuerungen sowie klinische Implikationen unter Berücksichtigung aktueller Entwicklungen im Gesundheitssystem beleuchtet.

Integrating heterogeneous data sources is vital for developing and validating robust medical machine learning models. Although the 12-lead format is standard in clinical electrocardiography (ECG), many datasets include only single-lead or vectorcardiogram (VCG) recordings. This study examines the transferability of 12-lead ECG data to VCG representations. Results show that ECG-VCG transfer depends on the acquisition system, whether clinical or Holter-based, and that the V6-X lead configuration achieves the most stable cross-lead performance.

Das 12-Kanal-Elektrokardiogramm (EKG) bleibt trotz erheblicher Fortschritte in der kardialen Bildgebung ein zentrales Instrument in der Diagnostik und Risikostratifizierung struktureller Herzerkrankungen. Dieser Übersichtsartikel beleuchtet die Bedeutung des Ruhe-EKG bei ischämischer Kardiomyopathie, hypertropher Kardiomyopathie (HCM), arrhythmogener rechtsventrikulärer Kardiomyopathie (ARVC) einschließlich der Differenzialdiagnose zur kardialen Sarkoidose sowie bei genetisch determinierten Formen der dilatativen Kardiomyopathie (DCM) und nichtdilatierten linksventrikulären Kardiomyopathie (NDLVC). Charakteristische elektrokardiographische Muster ermöglichen nicht nur die Identifikation zugrunde liegender myokardialer Substrate, sondern liefern teilweise auch prognostisch relevante Informationen hinsichtlich arrhythmogener Ereignisse und des Risikos für einen plötzlichen Herztod. Insbesondere bei genetischen Kardiomyopathien können elektrische Veränderungen der morphologischen Manifestation vorausgehen und somit eine frühe Phänotypisierung erlauben. Trotz limitierter Sensitivität einzelner Parameter bleibt das Ruhe-EKG ein breit verfügbares, kosteneffizientes und klinisch hochrelevantes Instrument, das integraler Bestandteil aktueller Leitlinienempfehlungen ist.

Pulmonary vein isolation (PVI) is the cornerstone of interventional treatment for atrial fibrillation. Patients with persistent atrial fibrillation have relatively high recurrence rates after catheter ablation irrespective of treatment strategy. Randomized data suggest that adding substrate modification to PVI at the first ablation procedure does not improve arrhythmia-free survival. To date, real-world data from experienced centers is limited. The German Ablation registry maintained by the Institut für Herzinfarktforschung Ludwigshafen, Germany included 909 patients with persistent atrial fibrillation (AF). 645 underwent isolated PVI (PVI-only) and 264 received additional substrate modification (PVI-plus). The primary endpoint was defined as freedom from AF after 1 year documented by ECG. Mean procedure time was longer in the PVI-plus group (203 ± 75 min vs. 186 ± 68 min; p = 0.002) with no significant difference in acute procedural success (94

BACKGROUND:Atrial fibrillation (AF) increases cardiovascular risk in patients with chronic kidney disease (CKD). The safety and efficacy of early rhythm control (ERC) in patients with CKD is not fully established. OBJECTIVES:This predefined secondary analysis of the EAST-AFNET 4 trial assessed the effectiveness and safety of ERC in patients with CKD defined by estimated glomerular filtration rate (GFR). METHODS:EAST-AFNET 4 randomized patients with recently diagnosed AF and comorbidities to ERC or usual care (UC). Key outcomes were analyzed by Kidney Disease Improving Global Outcomes defined CKD groups. The primary efficacy outcome combined cardiovascular death, stroke, hospitalization for worsening heart failure, or acute coronary syndrome. The safety outcome combined death, stroke, and serious rhythm control-related adverse events. Recurrent AF was a secondary outcome. RESULTS:Baseline creatinine was available in 2,742 of 2,789 (98.3%) patients. In this study, 23% had CKD (GFR: <60 mL/min/1.73 m2). Patients with CKD were older (CKD: 74 ± 7.4 years; no CKD: 69 ± 8.3 years; P < 0.001), had higher CHA2DS2-VASc scores (CKD: 4 ± 1.4; no CKD: 3.2 ± 1.2; P < 0.001), and more primary outcome events over 5.1 years of follow-up (HR: 0.98 per mL GFR decrease [95% CI: 0.97-0.99 per mL GFR decrease]). ERC reduced the primary outcome with and without CKD (no CKD: ERC: 3.4%/100 patient-years; UC: 4.1%/100 patient-years; HR: 0.84; P < 0.001; CKD: ERC: 5.8%/100 patient-years; UC: 8.5%/100 patient-years; HR: 0.67; P < 0.001; Pinteraction = 0.133). CKD increased safety outcomes without interaction with ERC (Pinteraction = 0.927). Patients with CKD experienced more AF recurrences with UC (Pinteraction = 0.036). CONCLUSION:ERC effectively and safely reduces cardiovascular events in patients with recently diagnosed AF and stroke risk factors with and without CKD. (Early Treatment of Atrial Fibrillation for Stroke Prevention Trial (EAST); NCT01288352).

Das aktualisierte Positionspapier der DGK zur Katheterablation von Vorhofflimmern (AF) [1] stellt die aktuelle Evidenz, Techniken und Qualitätsstandards dar, die sich seit 2017 gemeinsam mit Indikation, Technik und Rolle der Ablation in der Therapie deutlich gewandelt haben. Die Pulmonalvenenisolation (PVI) bleibt zentraler Bestandteil der AF-Ablation. Neben etablierten Verfahren wie Radiofrequenz- und Kryoablation gewinnt die Pulsed-Field-Ablation (PFA) an Bedeutung. Bei persistierendem AF fehlen klare Empfehlungen über die PVI hinaus, trotz zunehmender Daten für ergänzende Ablationsstrategien. Die Versorgungssituation zeigt eine starke Zunahme der Ablationen, wobei die tagesgleiche Entlassung nur für selektierte Patienten empfohlen wird. Die präzise Patientenselektion, inklusive Anamnese, Risikofaktoren und Bildgebung sind entscheidend für den Erfolg und die Sicherheit. Die Bedeutung von periprozeduralem Management und strukturierter Nachsorge wird hervorgehoben. Komplikationen wie Perikardtamponade, Schlaganfall und Phrenikusparese erfordern strukturierte Abläufe und erfahrene Teams. Besonders bei Patienten mit Herzinsuffizienz zeigt sich die Ablation als potenziell prognoseverbessernd. Die Zertifizierung von Zentren durch die DGK dient der Qualitätssicherung. Neue Entwicklungen wie KI-gestützte Ablationsplanung und Studien zur OAK-Strategie nach Ablation werden die Praxis weiter verändern.

Local anesthetics are widely used in medical care. However, their sodium channel blocking properties not only explain their analgesic potency but also their possible cardiotoxic effects. Due to the different pharmacodynamics and pharmacokinetics of different local anesthetics as well as the divergent cellular electrophysiological effects, we aimed to investigate and compare the electrophysiological effects of different local anesthetics in an established Langendorff model of the isolated rabbit heart. 50 hearts of New Zealand White rabbits were retrogradely perfused employing a Langendorff-setup. Eight catheters were placed endo- and epicardially, thereby recording monophasic action potentials. Hearts were paced at seven different cycle lengths (300–900 ms), thus obtaining cycle-length dependent action potential duration at 90

Mitral valve prolapse (MVP) is commonly benign, but an arrhythmic phenotype (AMVP) with increased risk for sudden cardiac death has been described. A prolonged Tpeak-Tend interval has been association with increased arrhythmic risk in different clinical settings. The aim of this study was to investigate a possible correlation between prolonged Tpeak-Tend interval and ventricular tachycardia (VT) inducibility in MVP. Sixty-five patients fulfilling the EHRA criteria of AMVP syndrome underwent programmed ventricular stimulation between 2016 and 2024. Sustained polymorphic VT was induced in 19 patients (29.2

Implantable cardioverter-defibrillator (ICD) is a cornerstone therapy for the prevention of sudden cardiac death. However, clinical profiles and in-hospital outcomes may differ according to device type—single-chamber ICD, dual-chamber ICD, or cardiac resynchronization therapy defibrillator (CRT-D). This study aimed to compare hospitalization parameters and peri-procedural complications among patients receiving these device types. We retrospectively analyzed 2,001 consecutive ICD recipients (single-chamber: 815; dual-chamber: 463; CRT-D: 723). Baseline characteristics, intensive care unit (ICU) utilization, procedure-related complications, and discharge outcomes were compared across groups. The main endpoint was defined as major adverse cardiovascular and cerebrovascular events (MACCE), and the second endpoint was defined as an extended MACCE including both MACCE and intensive care unit (ICU) admission. CRT-D recipients were older (67.5 ± 10.4 years, p < 0.01) and had a higher prevalence of comorbidities, including obesity (12.3

Aims Electrocardiogram (ECG) recordings are fundamental for diagnosing cardiac conditions. Recent advances in automatic ECG analysis have been dominated by deep learning, particularly convolutional neural networks (CNNs). CNNs excel in processing high-dimensional signal data, where their ability to automatically extract complex features has enabled significant progress. However, while CNNs are powerful for biomedical signal analysis, their application to ECG data also carries disadvantages, such as the requirement for large annotated datasets and limited explainability. To address these challenges, we aim to reintroduce shallow learning methods, such as linear classifiers, by leveraging the cyclic nature of ECG signals.Methods and results We developed an adaptive transformation that restructures ECG signals into a fully structured format suitable for shallow learning algorithms. This method aligns R-peaks across all signals in a dataset and resamples the inter-QRS segments to match a predefined reference heart rate. The approach was systematically evaluated across tasks including classification, clustering, and explainability. Our transformation substantially improved the performance of shallow learning techniques. Compared with CNN approaches, shallow models trained on transformed ECGs achieved superior accuracy and interpretability in data-limited scenarios.Conclusion We demonstrate that shallow machine learning methods, when combined with our alignment-based transformation, can reach CNN level performance in ECG analysis, especially under conditions of limited training data. This approach offers clear advantages in classification, clustering, and explainability and provides an accessible alternative to deep learning. To facilitate adoption and further research, we release a publicly available framework for ECG signal alignment at https://github.com/imi-ms/rlign.

The updated German Society of Cardiology (DGK) position paper on catheter ablation of atrial fibrillation (AF) [1] presents the current evidence, techniques, and quality standards, which have evolved significantly since 2017 alongside indications, technology, and the role of ablation in therapy. Pulmonary vein isolation (PVI) remains the cornerstone of AF ablation. In addition to established procedures such as radiofrequency and cryoballoon ablation, pulsed field ablation (PFA) is gaining importance. For persistent AF, clear recommendations beyond PVI are still lacking, despite growing evidence supporting adjunctive ablation strategies. The healthcare landscape shows a marked increase in ablations, with same day discharge procedures recommended only for carefully selected patients. Precise patient selection-including medical history, risk factors, and imaging-is critical for procedural success and safety. The importance of periprocedural management and structured follow-up is emphasized. Complications such as pericardial tamponade, stroke, and phrenic nerve injury require structured protocols and experienced teams. Particularly in patients with heart failure, ablation may offer prognostic benefits. Certification of centers by the DGK supports quality assurance. New developments, such as artificial intelligence (AI)-assisted ablation planning and studies on postablation anticoagulation strategies, are expected to further influence clinical practice.

Background:Esophageal fistula (EF) is a rare but devastating complication following atrial fibrillation (AF) ablation. Data regarding the impact of age on EF are scarce. Objective:To study the impact of age on the management and prognosis of EF following catheter ablation for AF. Methods:The POTTER-AF study is a worldwide registry on EF following catheter ablation for AF. A total of 553,729 patients underwent AF ablation in 214 centers between 1996 and 2022. Of them, 138 patients experienced EF, and data regarding age, management, and prognosis were available in 113 patients. The population was divided based on the median age. Results:The median age was 63 years; 54 patients were <63 years old (Group 1), and 59 patients were ≥63 years old (Group 2). The groups were similar regarding procedural characteristics. The older population had a shorter time to symptom onset [15.0 (6.0, 21.0) vs. 21.0 (10.0, 25.3) days; p = 0.031]. Group 2 was less likely to receive a brain CT or MRI for diagnosis (25.9% vs. 45.3%; p = 0.046). The older population was more likely to undergo endoscopic treatment without surgery (27.6% vs. 11.3%; p = 0.035). Conservative and surgical treatments were used in similar proportions. A trend toward higher fatality was noted in the older patients (72.9% vs. 56.6%; p = 0.078). Conclusion:The older population had a shorter time to symptom onset, was less likely to receive a brain CT or MRI, and more likely to be treated by an endoscopic approach only. The older patient group showed a trend toward a higher fatality.

Mitral valve prolapse (MVP) is commonly benign, but an arrhythmic phenotype (AMVP) with increased risk for sudden cardiac death has been described. Current risk stratification is mainly based on clinical data and imaging markers, while the role of programmed ventricular stimulation (PVS) remains uncertain. In this prospective single-center cohort study, 42 patients fulfilling the EHRA consensus criteria for AMVP underwent an electrophysiological study with programmed ventricular stimulation between 2016 and 2025. Stimulation was performed from the right ventricular apex and outflow tract using up to two extra stimuli. Following shared decision-making, patients received either an implantable cardioverter-defibrillator (ICD) or an implantable loop recorder (ILR). The endpoint was the occurrence of clinically significant ventricular arrhythmias (VAs), defined as appropriate ICD therapies, ILR-documented sustained VT, or arrhythmic syncope. Sustained ventricular arrhythmias were inducible in 20 patients (47.6

Background:Electrocardiogram (ECG) data constitutes one of the most widely available biosignal data in clinical and research settings, providing critical insights into cardiovascular diseases as well as broader health conditions. Advancements in deep learning demonstrate high performance in diverse ECG classification tasks, ranging from arrhythmia detection to risk prediction for various diseases. However, the widespread adoption of deep learning for ECG analysis faces significant barriers, including the heterogeneity of file formats, restricted access to pretrained model weights, and complex technical workflows for out-of-domain users. Objective:This study aims to address major bottlenecks in ECG-based deep learning by introducing ExChanGeAI, an open-source, web-based platform designed to offer an integrated, user-friendly platform for ECG data analysis. Our objective is to streamline the entire workflow-from initial data ingestion (regardless of device or format) and intuitive visualization to privacy-preserving model training and task-specific fine-tuning-making advanced ECG deep learning accessible for both clinical researchers and practitioners without machine learning (ML) expertise. Methods:ExChanGeAI incorporates robust preprocessing modules for various ECG file types, a set of interactive visualization tools for exploratory data analysis, and multiple state-of-the-art deep learning architectures for ECGs. Users can choose to train models from scratch or fine-tune pretrained models using their own datasets, while all computations are performed locally to ensure data privacy. The platform is adaptable for deployment on personal computers as well as scalable to high-performance computing infrastructures. We demonstrate the platform's performance on several clinically relevant classification tasks across 3 external and heterogeneous validation datasets, including a newly curated test set from routine care, evaluating both model generalizability and resource efficiency. Results:Our experiments show that de novo training with user-provided, task-specific data can outperform a leading foundation model, while requiring substantially fewer parameters and computational resources. The platform enables users to empirically determine the most suitable model for their specific tasks, based on systematic validations, while lowering technical barriers for out-of-domain experts and promoting open research. Conclusions:ExChanGeAI provides a comprehensive, privacy-aware platform that democratizes access to ECG analysis and model training. By simplifying complex workflows, ExChanGeAI empowers out-of-domain researchers to use state-of-the-art ML on diverse datasets, democratizing the access to ML in the field of ECG data. The platform is available as open-source code under the Massachusetts Institute of Technology (MIT) license.

BACKGROUND:Guidelines recommend catheter ablation for symptom relief in patients with atrial fibrillation. The aim of this trial was to ascertain whether catheter ablation improves atrial fibrillation-related quality of life more than a sham procedure. METHODS:PVI-SHAM-AF was a double-blind, multicentre, randomised trial conducted at nine study sites in Germany and Poland. Patients aged 18 years or older with symptomatic paroxysmal or persistent atrial fibrillation were randomly assigned in a 2:1 ratio to catheter ablation or a sham procedure using an automated online randomisation system with variable block sizes, stratified by trial site. The primary endpoint was the between-group difference in change from baseline to 6 months in the Atrial Fibrillation Effect on the Quality-of-life Questionnaire (AFEQT) summary score. The prespecified primary analysis was done in the intention-to-treat population and included all randomly assigned patients, with missing data handled by multiple imputation. This trial is registered with ClinicalTrials.gov (NCT05119231) and 12-month follow-up is ongoing. FINDINGS:Between Nov 12, 2021, and Nov 3, 2025, 1199 patients were invited to participate in the study and 262 patients consented and were randomly assigned: 173 patients to catheter ablation and 89 to sham. The median age was 67 years (IQR 62-73); 134 (51%) were female and 128 (49%) were male. Median follow-up was 184 days (IQR 181-191). At 6 months, the mean AFEQT summary score had increased from 61·3 (SD 20·1) to 81·1 (16·6) in the catheter ablation group and from 59·2 (19·0) to 74·9 (19·5) in the sham control group. The Hodges-Lehmann estimate of the between-group difference in change was 2·6 (95% CI -2·7 to 8·0; p=0·36). One death occurred in each group; neither was considered related to the study procedure. Serious adverse events adjudicated as related or possibly related to the study procedure occurred in ten unique patients: six patients in the catheter ablation group and four patients in the sham control group. One of these was an ischaemic stroke occurred in the sham control group. INTERPRETATION:Catheter ablation did not demonstrate superiority over a sham procedure for improving atrial fibrillation-related quality of life at 6 months. FUNDING:Helios Gesundheit (Förderung Leipziger Herzmedizin).

While VT ablation is increasingly recognized as effective, its real-world efficacy, risks, and outcomes require further investigation. This study aims to assess VT ablations in a real-world scenario using data from the German VIDEO registry. We analyzed 801 ICD patients hospitalized with VT within the German VIDEO registry between 2018 and 2023. Among these, 145 patients (18